Search Results (573)

Early and accurate detection of skin cancer is critical for reducing mortality rates, particularly for malignant melanoma. Automated analysis of dermoscopic images has gained significant attention due to its potential to support clinical diagnosis and overcome the limitations of manual inspection. Motivated by challenges such as image noise, low contrast, lesion variability, and redundant feature representation, this study proposes an optimal deep hybrid framework for skin lesion detection and classification. The objective of this work is to design a robust and efficient system that integrates advanced preprocessing, precise segmentation, optimal feature selection, and accurate classification. Initially, contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE) and noise reduction using Wiener filtering are applied to improve image quality. Lesion regions are then segmented using a Selective Kernel U-Net (SK-UNet), which adaptively captures multi-scale spatial information. Subsequently, discriminative color, texture, and shape features are extracted and optimized using the Fossa Optimization Algorithm (FOA) to eliminate redundancy. A hybrid one-dimensional Convolutional Neural Network–Gated Recurrent Unit (1D-CNN–GRU) classifier is employed for final classification, learning both spatial and sequential feature patterns. Experimental evaluation on the ISIC and DermMNIST datasets demonstrates that the proposed framework achieves classification accuracies of 97.6% and 95.6%, respectively, outperforming several existing methods. The results confirm that the proposed hybrid framework provides reliable, accurate, and scalable skin cancer diagnosis, highlighting its potential for assisting clinical decision-making and early detection. Full article

Carbon emissions from crop farming are a critical component of carbon emissions from land use. This study focuses on crop farming in the Yangtze River Economic Belt. The carbon emission coefficient method, the LMDI model, the Tapio decoupling model, and the GM(1,1) gray forecasting model were employed to systematically analyze the spatiotemporal evolution, driving mechanisms, decoupling effects, and future trends of carbon emissions from crop farming in the Yangtze River Economic Belt, based on panel data from 11 provinces (municipalities) covering the period 2013–2024. The results show that the total carbon emissions from crop farming in the Yangtze River Economic Belt exhibit an inverted “U”-shaped pattern, rising initially and then declining, while carbon emission intensity continues to decrease. In terms of emission sources, methane emissions from paddy fields account for the highest proportion, emissions from agricultural inputs show a steady decline, and emissions from soil use continue to rise. Regarding driving factors, crop farming efficiency is the most significant negative driver, while regional economic development serves as the primary positive driver; the decoupling pattern has gradually transitioned from “weak decoupling” to a predominantly “strong decoupling” pattern; projection results indicate that both carbon emissions and emission intensity from crop farming in the Yangtze River Economic Belt will generally decline in the future, though regional pressure for emission reductions remains significant; agricultural industrial structures should be optimized and adjusted, with efforts focused on promoting the standardized and scaled development of organic and ecological agriculture to facilitate the green and low-carbon transformation of agriculture. Full article

This study examines why currency substitution proves so difficult to reverse, even after countries succeed in stabilizing inflation. Focusing on Bolivia, Brazil, Mexico, and Turkey—economies that endured severe inflationary episodes before implementing stabilization programs—the paper asks a simple but important question: why does reliance on foreign currency persist long after inflation has been brought down? To answer this, the analysis adopts a structural time-series state-space framework that allows behavioral parameters to evolve gradually over time. Rather than assuming persistence, the model lets it emerge from the data and, crucially, compares alternative ways in which agents might form expectations about exchange rate movements. The evidence reveals a consistent pattern. By the end of the sample period, currency substitution remains statistically and economically significant in all four countries. The dominant expectation mechanism is extrapolative: agents tend to look at recent depreciation and assume it will continue. This tendency creates a reinforcing loop—when currencies depreciate, expectations of further depreciation strengthen, and the incentive to hold foreign currency intensifies. What makes these findings particularly striking is that this dynamic does not vanish once inflation is stabilized. Even in periods of relative macroeconomic calm, substitution persists. Past instability leaves a lasting imprint on expectations, and concerns about the durability of policy reforms continue to shape monetary behavior. In several cases, ongoing depreciation against the U.S. dollar further validates these cautious beliefs. As a result, the findings suggest that currency substitution is not merely a mechanical residue of past inflation. It is sustained by the way people form and update expectations in environments marked by credibility challenges. Stabilizing inflation is therefore a necessary step, but it is not enough on its own. Durable confidence in the domestic currency requires rebuilding credibility in a way that gradually reshapes expectations and restores trust over time. Full article

The rapid expansion of digitalization is reshaping factor mobility and income distribution between urban and rural areas, with important implications for inclusive and sustainable development. Using panel data for 277 prefecture-level cities in China from 2012 to 2022, this study examines how DE affects urban–rural income disparity from the perspectives of nonlinear effects, factor allocation, and spatial interdependence. Compared with existing studies based mainly on provincial data, this paper provides a more fine-grained analysis at the prefecture level and combines mediation, double-threshold, and spatial analysis within a unified framework. The results show that DE has a significant U-shaped effect on urban–rural income disparity, suggesting that digital development may initially narrow the gap but widen it after a certain stage. Urban–rural factor allocation acts as an important transmission channel, and its role exhibits a double-threshold characteristic. The effect of DE also varies across urban agglomeration types and stages of urbanization, with stronger impacts in more developed and urbanized regions. In addition, the direct effect of DE follows a U-shaped pattern, whereas its spatial spillover effect shows an inverted U-shape. These findings indicate that digitalization is not automatically equalizing and that its distributional consequences depend on factor allocation conditions, regional development stages, and spatial linkages. The study provides evidence for policies aimed at reducing urban–rural inequality and promoting more balanced and sustainable development. Full article

The deformation of surrounding soil primarily governs the behavior of underground structures. Consequently, variations in their external geometry significantly affect their overall seismic response. Moreover, large soil deformations and structural uplift caused by liquefaction severely threaten their seismic safety. While most previous studies have focused on conventional rectangular subway stations, the seismic performance of novel varying-span structures remains largely unexplored. In this study, nonlinear dynamic time-history analyses are conducted to investigate the soil–structure interaction (SSI) of large unequal-span subway stations in liquefiable sites. Furthermore, the seismic responses of both the structure and the surrounding soil are systematically evaluated under various burial depths of the liquefiable layer. Finally, a U-shaped foundation reinforcement method is proposed to mitigate structural uplift. The results show that unequal-span structures suppress liquefaction in lateral soil, whereas significant liquefaction occurs beneath the base slab and cantilevered middle slabs. The burial depth of the liquefiable layer has a negligible effect on the liquefaction state directly under the center span. Regarding structural response, global uplift follows a spatial pattern that peaks at the center span and gradually attenuates laterally. Although the proposed U-shaped reinforcement effectively reduces both total and differential uplift, it does not fundamentally change the underlying liquefaction mechanism. Specifically, reinforcing the soil under cantilevered sections minimizes differential uplift while enhancing the overall economic efficiency of the seismic design. These findings provide a scientific basis for optimizing the seismic resilience of complex underground structures, contributing to the development of resource-efficient and disaster-resilient urban underground infrastructure in liquefaction-prone regions. Full article

This study provides an early evaluation of the effectiveness of the Core Tax Administration System, a digital taxation platform introduced to integrate all tax administration processes in Indonesia into a single system. To conduct this evaluation, the study integrates two of the most established frameworks in the information systems literature, namely the DeLone and McLean Information Systems Success Model and the Technology Acceptance Model. Tax professionals are involved in the evaluation process because they are the primary users of the system and possess advanced knowledge of taxation. Structural equation modeling is employed as the analytical technique. The results indicate that system usage generates individual-level benefits by reducing perceived compliance costs, which in turn translate into organizational-level outcomes in the form of increased tax compliance intentions. However, the non-linear effect analysis reveals that this relationship is not entirely linear but follows an inverted U-shaped pattern. This finding suggests that over time, highly routine system usage may reduce professional vigilance by fostering excessive reliance on automated features and superficial processing. Such dependence can weaken perceived efficiency gains and diminish intrinsic motivation for careful and accurate reporting, highlighting the importance of balancing efficiency with system design features that support professional judgment and vigilance. Full article

In the context of the “dual carbon” goals, this study examines the spatiotemporal patterns and evolution of urban low-carbon coordinated development (LCCD). Based on the integrated Economy–Energy–Environment–Society (3E1S) framework, this study constructs a multidimensional evaluation index system for urban LCCD and applies a composite system coordination degree model to quantitatively assess and analyze the spatiotemporal evolution of LCCD across 271 prefecture-level and above cities in China from 2005 to 2020. The results indicate that (1) from a temporal perspective, the level of urban LCCD in China exhibits an overall upward trend during the study period, with relatively rapid growth from 2005 to 2015, a subsequent slowdown after 2015, and a stage-wise decline observed in 2020, reflecting a transition from rapid improvement to gradual adjustment; (2) from a spatial perspective, urban LCCD demonstrates a certain degree of spatial autocorrelation and an overall spatial structure characterized by a southwest–northeast-oriented axis, with spatial agglomeration features gradually strengthening over time; (3) from a system structure perspective, the coordinated evolution of the 3E1S subsystems shows clear differentiation, with the energy and economic subsystems following an inverted U-shaped trajectory, the environmental subsystem exhibiting a fluctuating upward trend, and the social subsystem maintaining continuous improvement, highlighting the inherent imbalance in the multidimensional process of subsystem coordination. From a multisystem coordination perspective, this study systematically identifies the spatiotemporal evolutionary characteristics and subsystem coupling relationships of urban low-carbon coordinated development, providing empirical evidence for a deeper understanding of multidimensional low-carbon coordination processes in cities. Full article

Industrial digitalization reshapes production processes and can potentially improve carbon productivity by optimizing factor allocation and energy efficiency. Using panel data for 30 Chinese provinces from 2012 to 2022, this study constructs a comprehensive industrial digitalization index with four dimensions and 13 indicators using the entropy method and examines its impact on carbon productivity (GDP per unit of CO₂ emissions). We employ the Dagum Gini coefficient and kernel density estimation to describe regional disparities and their evolution, a dynamic panel threshold model to test the nonlinear role of industrial transformation and upgrading, and a spatial Durbin model to identify spatial spillover effects. The results indicate that industrial digitalization has risen nationwide but remains uneven; industrial digitalization significantly enhances carbon productivity, with stronger effects in the eastern and western regions and in plain areas; the effect exhibits a double-threshold pattern with respect to industrial transformation and upgrading, implying a U-shaped relationship; and industrial digitalization generates positive spatial spillovers. These findings suggest that policy should coordinate digital infrastructure investment with industrial upgrading and regional collaboration to accelerate low-carbon, high-efficiency growth. Full article

Amidst the polycrisis of 2018–2024, Asia-Pacific trade flows exhibited a structural resilience that contrasts with traditional theoretical predictions of severe trade contraction under high uncertainty. This study investigates these resilience dynamics using a structural gravity model estimated via the Poisson Pseudo Maximum Likelihood (PPML) approach. The analysis utilizes a balanced panel of 14 key regional economies (N = 4914), explicitly disaggregated into geographic (ASEAN-6 vs. non-ASEAN) and global value chain (high vs. low GVC intensity) subgroups to capture heterogeneous responses. The empirical results confirm that economic policy uncertainty (EPU) acts as a significant trade friction (β = −3.371), consistent with the wait-to-invest mechanism of real options theory. However, this effect is heterogeneous and significantly mitigated by institutional frameworks. We identify a robust institutional shield effect, where participation in trade agreements effectively neutralizes the adverse transmission of policy shocks (interaction coefficient = 3.396). Furthermore, this study uncovers a structural break during periods of extreme geopolitical conflict, characterized by a convex U-shaped relationship between uncertainty and trade. This pattern provides macro-level evidence of a behavioral shift in regional supply chains from a just-in-time cost-efficiency optimization model to a just-in-case security maximization paradigm, consistent with precautionary inventory accumulation. These findings underscore the critical role of modern trade pacts as institutional credibility anchors and the necessity of adaptive strategies in navigating heightened macroeconomic volatility. Full article

Background: Type 2 diabetes mellitus (T2DM) is characterized by chronic low-grade inflammation that contributes to cardiometabolic complications. While diabetes duration reflects cumulative metabolic exposure, its relationship with systemic inflammatory burden remains insufficiently defined. We aimed to investigate inflammatory patterns across diabetes duration and to explore their metabolic and cardio–renal correlates. Methods: This real-world cross-sectional study included 250 adults with T2DM. Diabetes duration was analyzed both continuously and across four predefined strata (0–4, 5–9, 10–14, and ≥15 years). Inflammatory burden was assessed using C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR). Given the skewed distribution of CRP, log-transformed CRP was used in regression analyses. Nonlinear associations were evaluated using quadratic regression models. This approach was selected because preliminary descriptive analyses suggested a non-monotonic relationship between diabetes duration and CRP levels. Inclusion of a quadratic term allowed formal testing of a potential curvilinear association between diabetes duration and inflammatory burden. Spearman correlations were performed to assess associations with metabolic, renal, and cardiovascular variables. Results: CRP showed a nonlinear cross-sectional association across diabetes duration strata. Median CRP values were higher in early (0–4 years: 0.62 mg/L) and long-standing diabetes (≥15 years: 0.77 mg/L) compared with intermediate-duration groups (p = 0.063). Quadratic regression confirmed a U-shaped relationship (adjusted β_duration = −0.079, p < 0.001; β_duration² = 0.0027, p < 0.001; R² = 0.326). ESR differed significantly across duration strata (p = 0.002), with the highest levels observed in long-standing diabetes. CRP correlated positively with BMI (ρ = 0.151; p = 0.017) and triglyceride-to-HDL ratio (ρ = 0.215; p < 0.001), but not with HbA1c. Both CRP and ESR were more strongly associated with functional CKD (ρ = 0.350 and 0.429, respectively; p < 0.001) than with ASCVD. Conclusions: Inflammatory burden in T2DM shows a nonlinear cross-sectional pattern across diabetes duration, characterized by elevated levels in early and long-standing disease. Systemic inflammation appears more closely linked to renal dysfunction than to established cardiovascular disease. These findings support a cardio–renal–inflammatory axis in which prolonged diabetes exposure contributes to renal decline, which in turn amplifies systemic inflammatory activation. Full article

Background: Qualitative motion analysis revealed that the cervical spine moves according to a consistent pattern. Current data analysis methods are limited by the extensive time required to process the retrieved data. A previous study demonstrated the feasibility of using a deep-learning model to automate analysis methods. However, segmentation accuracy needed to be improved. This study aims to improve segmentation model performance to enable reliable motion analysis. Methods: Four nnU-Net configurations were tested: baseline (A), pre-trained (B), with histogram equalization (C), and pre-trained with histogram equalization (D). Segmentation performance was evaluated using Dice Similarity Coefficient (DSC), Intersection over Union (IoU) and 95th percentile Hausdorff Distance (HD95). Vertebral rotation was estimated using mean shapes. Reliability was assessed using the Intraclass Correlation Coefficient (ICC). Sensitivity analyses were conducted. Results: Across all models, mean DSC ranged from 0.67 to 0.92, mean IoU from 0.55 to 0.85, and mean HD95 from 2.35 to 19.67 mm. After sensitivity analysis for low segmental range of motion (sROM) and low-quality recordings, the mean ICC ranged from 0.617 to 0.837 for model A, from 0.609 to 0.780 for model B, from 0.409 to 0.689 for model C, and from 0.480 to 0.835 for model D. Conclusions: This study shows that Models A and B can accurately analyze cervical motion patterns. High image contrast and an adequate sROM are essential for robust model performance. It also marks an important step toward automated qualitative motion analysis, increasing the accessibility of motion pattern evaluation. Full article

Urban network externalities have emerged as a novel impetus for regional economic growth. However, the extent to which inter-urban network connections promote regional economic growth and the associated spatiotemporal heterogeneity remain underexplored. This study constructs a multi-dimensional urban network framework from the perspectives of enterprise linkages, infrastructure connectivity, and innovation collaborations, capturing the multifaceted nature of intercity relationships and their critical role in shaping regional development. Utilizing the Cobb–Douglas production function and the spatial Durbin model, the study quantitatively assesses the impact of urban network externalities on economic growth and examines the spatiotemporal heterogeneity of these impacts. The main findings are as follows: Urban network externalities generally exert a positive influence on regional economic growth, yet this effect exhibits significant regional and city-size heterogeneity. Regions with more developed networks experience stronger growth effects from these externalities. Moreover, large cities benefit more substantially from network integration compared to small and medium-sized cities. Spatial decomposition of effects further reveals that urban network externalities promote economic growth through both local direct effects and spillover effects to neighboring areas. Approximately 70% of the economic growth contribution originates from direct effects within the region, while nearly 30% stems from spillover effects from adjacent regions. Additionally, the spatial spillover effects display clear distance decay, following an inverted U-shaped pattern with a bimodal distribution. Significant spillover effects are observed within 380 km, peaking at 180 km and 340 km. Full article

Enhancing the allocation efficiency of hydropower resources is critical to achieving China’s carbon peaking and carbon neutrality goals. Based on panel data of 29 Chinese regions from 2001 to 2020, this study first measures the degree of hydropower resource misallocation via a counterfactual decomposition approach, and then adopts a threshold model to explore the impact of green finance on hydropower resource misallocation. The results show that: (1) Western and southwestern regions with abundant hydropower resources yet insufficient economic absorption capacity suffer from hydropower oversupply, while eastern coastal and central regions with advanced economies and intensive industries face hydropower undersupply. The inverse spatial distribution pattern of hydropower supply and demand cores reflects prominent hydropower resource misallocation. (2) Green finance has an inverted U-shaped nonlinear relationship with hydropower resource misallocation. Moderate development of green finance can improve hydropower resource allocation efficiency, yet exceeding the optimal threshold may trigger problems including greenwashing and thus exacerbate hydropower resource misallocation. Full article

Music popularity prediction is a fundamental problem in music information retrieval, with important implications for digital content dissemination and creative decision-making on streaming platforms. In this study, music popularity prediction is formulated as a supervised regression problem, and six widely-used tree ensemble models (Random Forest, XGBoost, CatBoost, LightGBM, Extra Trees, and Decision Tree) are systematically evaluated using large-scale Spotify data. Among these models, Random Forest achieves the best predictive performance on this dataset (RMSE = 6.79, MAE = 5.10, and $R^2$ = 0.6658), followed by Extra Trees ($R^2$ = 0.6378) and Decision Tree ($R^2$ = 0.6328). Bayesian hyperparameter optimization based on a Tree-structured Parzen Estimator with an Expected Improvement acquisition function is conducted over 50 trials with 5-fold cross-validation to ensure robust model selection. Shapley value decomposition via SHAP analysis reveals that temporal recency dominates feature importance, far surpassing traditional musical attributes, while acoustic intensity (loudness) exhibits a U-shaped contribution pattern with optimal values at moderate intensity levels. Further SHAP dependence analysis uncovers non-linear relationships, indicating substantial popularity advantages for recent releases and optimal loudness levels around $-5$ to 0 dB. These findings suggest that streaming popularity is primarily governed by temporal exposure dynamics and production-related characteristics rather than intrinsic musical structure, offering both theoretical insights for music information retrieval research and suggestive empirical patterns that may inform future investigations into digital music ecosystems. Full article

Based on 2011–2022 panel data covering 278 Chinese cities, a panel fixed-effects model, a mediating effect model, and a threshold regression model are used to conduct an empirical analysis of the influence of the digital economy (DE) on urban carbon emission performance from the quantitative and efficiency perspectives. The key findings include the following: (1) An inverted U-relationship is observed between the DE development and urban per capita carbon emissions (PCE), while the nexus between the DE and carbon emission efficiency (CEE) follows a U-shaped pattern. (2) The DE yields a stronger carbon reduction effect once green technology innovation attains elevated levels; conversely, under conditions of nascent green innovation, its principal impact manifests through improvements in CEE. Only when green technology innovation surpasses a critical threshold does the DE begin to reduce carbon emissions. (3) Heterogeneity analysis indicates that, in optimization and upgrading agglomerations, carbon emissions are reduced by DE at a later time point. In growth and expansion agglomerations, the impact of DE on CEE is more evident. Moreover, policy priorities should include fostering innovation-driven digitalization, expanding green technology diffusion, and optimizing regional mechanisms for coordinated low-carbon growth. Full article